<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1006">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Kernel-Based Pronoun Resolution with Structured Syntactic Knowledge</Title>
  <Section position="4" start_page="41" end_page="41" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> One of the early work on pronoun resolution relying on parse trees was proposed by Hobbs (1978).</Paragraph>
    <Paragraph position="1"> For a pronoun to be resolved, Hobbs' algorithm works by searching the parse trees of the current text. Specifically, the algorithm processes one sentence at a time, using a left-to-right breadth-first searching strategy. It first checks the current sentence where the pronoun occurs. The first NP that satisfies constraints, like number and gender agreements, would be selected as the antecedent.</Paragraph>
    <Paragraph position="2"> If the antecedent is not found in the current sentence, the algorithm would traverse the trees of previous sentences in the text. As the searching processing is completely done on the parse trees, the performance of the algorithm would rely heavily on the accuracy of the parsing results.</Paragraph>
    <Paragraph position="3"> Lappin and Leass (1994) reported a pronoun resolution algorithm which uses the syntactic representation output by McCord's Slot Grammar parser. A set of salience measures (e.g. Subject, Object or Accusative emphasis) is derived from the syntactic structure. The candidate with the highest salience score would be selected as the antecedent. In their algorithm, the weights of Category: whether the candidate is a definite noun phrase, indefinite noun phrase, pronoun, named-entity or others. Reflexiveness: whether the pronominal anaphor is a reflexive pronoun.</Paragraph>
    <Paragraph position="4"> Type: whether the pronominal anaphor is a male-person pronoun (like he), female-person pronoun (like she), single gender-neuter pronoun (like it), or plural gender-neuter pronoun (like they) Subject: whether the candidate is a subject of a sentence, a subject of a clause, or not.</Paragraph>
    <Paragraph position="5"> Object: whether the candidate is an object of a verb, an object of a preposition, or not.</Paragraph>
    <Paragraph position="6"> Distance: the sentence distance between the candidate and the pronominal anaphor.</Paragraph>
    <Paragraph position="7"> Closeness: whether the candidate is the candidate closest to the pronominal anaphor.</Paragraph>
    <Paragraph position="8"> FirstNP: whether the candidate is the first noun phrase in the current sentence.</Paragraph>
    <Paragraph position="9"> Parallelism: whether the candidate has an identical collocation pattern with the pronominal anaphor.</Paragraph>
    <Paragraph position="10">  olution system salience measures have to be assigned manually.</Paragraph>
    <Paragraph position="11"> Luo and Zitouni (2005) proposed a coreference resolution approach which also explores the information from the syntactic parse trees. Different from Lappin and Leass (1994)'s algorithm, they employed a maximum entropy based model to automatically compute the importance (in terms of weights) of the features extracted from the trees. In their work, the selection of their features is mainly inspired by the government and binding theory, aiming to capture the c-command relationships between the pronoun and its antecedent candidate. By contrast, our approach simply utilizes the parse trees as a structured feature, and lets the learning algorithm discover all possible embedded information that is necessary for pronoun resolution. null</Paragraph>
  </Section>
class="xml-element"></Paper>